Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real behavior beyond them: opt-outs are removed from the reach count, and topic_id further excludes contacts unsubscribed from that topic, which is exactly the kind of counting semantics an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with a parenthetical that carries the only nuance needed. No filler, no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully conveys that two counts come back (segment match count and broadcast reach) and how each is filtered. Return field names and error conditions for an invalid id are unstated, but the essentials for calling it correctly are present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3; the description goes slightly beyond the schema by explaining that the topic filter also strips contacts unsubscribed from that topic, not just non-subscribers. The required id parameter is still only described by the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (count) and resource (contacts matched by a segment), plus the second number returned (broadcast reach). It does not explicitly differentiate itself from the similar sibling query_audience, but the counting-only scope is clear from the wording.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: 'right now' suggests a live, non-cached pre-send check and the topic_id clause hints at a topic-scoped send audience. There is no explicit when-to-use/when-not guidance versus get_segment or query_audience.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.